Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Reversing direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wheel
    -0.07
    Eventually
    -0.07
    'A
    -0.06
     Wolver
    -0.06
    Conn
    -0.06
     بزرگ
    -0.06
     Gor
    -0.06
    -cell
    -0.06
    さんの
    -0.06
     marzo
    -0.06
    POSITIVE LOGITS
     Polyester
    0.07
     fasting
    0.07
     lửa
    0.07
    arkin
    0.06
    ança
    0.06
    .zone
    0.06
    аров
    0.06
    ornado
    0.06
    HTTPRequest
    0.06
     immense
    0.06
    Act Density 0.034%

    No Known Activations